{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/object-aware-domain-generalization-for-object","title":"Object-Aware Domain Generalization for Object Detection","arxiv_id":"2312.12133","date":"2023-12-19","proceeding":null,"authors":["Wooju Lee","Dasol Hong","Hyungtae Lim","Hyun Myung"],"abstract":"Single-domain generalization (S-DG) aims to generalize a model to unseen environments with a single-source domain. However, most S-DG approaches have been conducted in the field of classification. When these approaches are applied to object detection, the semantic features of some objects can be damaged, which can lead to imprecise object localization and misclassification. To address these problems, we propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection. Our method consists of data augmentation and training strategy, which are called OA-Mix and OA-Loss, respectively. OA-Mix generates multi-domain data with multi-level transformation and object-aware mixing strategy. OA-Loss enables models to learn domain-invariant representations for objects and backgrounds from the original and OA-Mixed images. Our proposed method outperforms state-of-the-art works on standard benchmarks. Our code is available at https://github.com/WoojuLee24/OA-DG.","url_abs":"https://arxiv.org/abs/2312.12133v1","url_pdf":"https://arxiv.org/pdf/2312.12133v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"object-aware-domain-generalization-for-object","repo_url":"https://github.com/WoojuLee24/OA-DG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"robust-object-detection","task_name":"Robust Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"oa-loss","method_name":"OA-Loss"},{"method_slug":"oa-mix","method_name":"OA-Mix"}],"datasets_introduced":[],"methods_introduced":[{"slug":"oa-loss","name":"OA-Loss","full_name":"Object-Aware Loss"},{"slug":"oa-mix","name":"OA-Mix","full_name":"Object-Aware Mix"}],"results":[{"leaderboard":"/sota/robust-object-detection-on-cityscapes-1","task":"Robust Object Detection","dataset":"Cityscapes","model":"OA-DG","rank_in_archive_order":5,"of":13,"metrics":{"mPC [AP]":"21.8"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-cityscapes-1","task":"Robust Object Detection","dataset":"Cityscapes","model":"OA-Mix","rank_in_archive_order":7,"of":13,"metrics":{"mPC [AP]":"20.8"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-dwd","task":"Robust Object Detection","dataset":"DWD","model":"OA-DG","rank_in_archive_order":5,"of":12,"metrics":{"mPC [AP50]":"31.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.12133","atlas_url":"https://app.syntology.ai/?focus=2312.12133","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}